Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kensaurus/cursor-kenji --skill plan-error-handlinggit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kensaurus/cursor-kenji/plan-error-handling)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/plan-error-handling"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/plan-error-handling/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/plan-error-handling"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/plan-error-handling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.02204 |
| Opus 5 | $0.00028 | $0.01102 |
| Sonnet 5 | $0.00011 | $0.00441 |
| Haiku 4.5 | $0.00006 | $0.00220 |
Grade A, and why
plan-error-handling scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error-Handling & Observability Audit + Fix Plan
Degree of freedom: HIGH — map silent paths, score, plan. Stay plan-only. No code or SDK edits until each phase is approved.
This skill vs neighbors
| Skill | Owns |
|---|---|
| plan-error-handling (this) | Silent-failure + Sentry/Langfuse plan |
debug-sentry-monitor |
Live Sentry triage |
audit-langfuse-llm |
LLM eval / trace quality |
How to reason (every plan item)
- Propose — report, init, redact, or wrap a silent path
- Risk — what fails in prod with no signal (or PII leaving the env)
- Keep-working — surfaces that already capture and sanitize
- Phase — swallows → coverage → redaction → LLM traces (do not execute)
Worked example
Propose: report + rethrow the empty catch on
api/pay.tscharge; init Sentry on the edge surface. Risk: payment failures produce no event — you only hear from the user. Keep-working: web client already captures unhandled exceptions. Phase: Phase 1 — stop silent failures.
Role: Senior reliability engineer + observability specialist.
Task: Map every silent-failure path across Sentry and Langfuse planes, score by
blast radius × invisibility, phase remediations, emit plan-error-handling.md.
Audit & plan only — no code or SDK edits until each phase is approved.
Find what fails in silence. Make it observable. Change nothing until approved.
AI coding agents optimize for making the error message go away, not for making
failure visible. Error-handling gaps are nearly twice as common in AI-generated
pull requests as in human ones — empty catch blocks, missing guards, unhandled
promise rejections, and handlers that leak stack traces into capture systems. The
dangerous part isn't the crash you see; it's the failure you don't.
This skill is the audit-and-plan half. Execution goes to backend-observability /
audit-langfuse-llm after you approve each phase.
When this fires
Trigger phrases: "errors don't reach Sentry", "it fails silently", "empty catch blocks", "add error handling", "why can't I debug prod", "check my Langfuse traces", "my LLM costs are a mystery", "pre-launch observability".
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 208 lines · 57 tokens per session scan A 12ff4a4650d4
plan-error-handling is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 11d ago), licensed MIT. It adds 57 tokens to every session and 2,204 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
debugging
Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.
lcx-report-bug
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.
ast-grep
Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.
lcx-doctor
Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, lazycodex-ai, omo-codex, or Codex behaves oddly after an install, update, or config change, suspects a stale, drifted, or broken setup, or wants the local install…
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.